Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Kiro & Claude: AI Architecture Diagrams
Generate enterprise architecture diagrams and documentation automatically from natural language using AI-powered Kiro and Claude Code Skills, significantly reducing manual effort and ensuring consistency.
I built an AI-powered architecture documentation accelerator using Kiro and Claude Code Skills that automatically generates enterprise architecture artifacts from natural language requirements and existing documentation.
In large organizations, portfolio architects spend significant time manually creating logical architecture diagrams, physical architecture diagrams, deployment diagrams, process flows, data flow diagrams, and supporting IT documentation. This process is repetitive, time-consuming, and often results in inconsistent outputs across teams.
For this project, I created a reusable skill framework that enables architects to generate these artifacts automatically through AI-assisted workflows.
During the demo, I will show:
How architects provide requirements using simple prompts
The custom Kiro/Claude Code Skills that orchestrate diagram generation
Automated creation of logical, physical, deployment, process flow, and data flow diagrams
Generation of supporting architecture documentation
The end-to-end workflow from requirements to architecture deliverables
Real examples demonstrating significant reductions in documentation effort and turnaround time
- Claude CodeAnthropic's agentic coding tool: Unleash Claude's raw power directly in your terminal or IDE to turn complex, hours-long workflows into a single command.Claude Code is Anthropic’s powerful agentic coding assistant, designed for high-velocity development. It operates natively within your terminal, IDE (VS Code, JetBrains), or via a web interface, allowing you to delegate complex tasks like feature building, bug fixing, and codebase navigation. The agent plans, edits files, executes commands, and creates commits, maintaining awareness of your entire project structure. Internally, Anthropic engineers using Claude Code reported a 67% increase in productivity, demonstrating its capacity to deliver significant gains for Pro and Max plan users.
- Kiro SkillsKiro Skills are portable, open-standard instruction packages that dynamically load specialized workflows and team conventions into your AI coding agent on demand.Kiro Skills solve the context-overload problem in AI-assisted development by utilizing progressive disclosure: the agent registers only basic metadata at startup, loading full instruction sets, scripts, and templates exclusively when triggered by user intent or slash commands (like /pr-review). Built on the open Agent Skills standard, these markdown-driven packages live directly inside your repository (under .kiro/skills/) or globally on your machine, ensuring your development agent executes complex, multi-step tasks (such as Terraform deployments or API integrations) with precise, project-specific context.
- DrawA free, open-source diagramming application built for secure, collaborative technical drawing.Draw (widely known as draw.io) is a security-first diagramming tool designed for teams mapping out complex architectures, flowcharts, and network designs. Operating under an Apache 2.0 license, it bypasses the typical enterprise paywalls and artificial scarcity of VC-backed competitors, giving over 100 million users worldwide free access to professional-grade tools. The platform prioritizes absolute data privacy by storing files directly on your preferred cloud storage (such as Google Drive, OneDrive, or GitHub) or locally on your desktop. With native integrations for Atlassian Confluence, Jira, and VS Code, it fits seamlessly into developer workflows, offering robust shape libraries and real-time cursor collaboration without requiring a sign-up.
- Natural Language ProcessingNatural Language Processing (NLP) is the AI subfield that engineers computers to read, interpret, and generate human language: bridging the communication gap between man and machine.NLP is the core technology enabling machines to process human text and speech, combining computational linguistics with deep learning models (like LLMs). This capability powers critical, high-volume applications: sentiment analysis on millions of customer reviews, real-time machine translation (Google Translate), and conversational AI assistants (Siri, Alexa). Specific techniques include tokenization, named entity recognition, and dependency parsing. The goal is clear: extract meaning, classify intent, and automate language-based tasks, driving efficiency gains across customer service and data analysis operations.
- Architecture Diagram GenerationGenerate professional, code-backed system architecture diagrams instantly from plain-text prompts.Eraser AI transforms written system requirements, technical specs, or simple prompts into production-ready architecture diagrams in seconds. By combining a natural language interface with a robust diagram-as-code engine, it eliminates the tedious manual alignment of traditional vector tools (like Visio or Draw.io). Developers and cloud architects can instantly map out complex AWS, Azure, or GCP infrastructures, generate sequence diagrams, and keep documentation in sync with code repos using Markdown-based syntax. It is the fastest way to turn a rough technical concept into a clean, presentation-grade visual during design reviews.
Compose Email
Loading recent emails...